PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Risk bounds for transduction and semi-supervised learning relative to data structure
Guy Lever
AISTATS 2010 2010.

Abstract

We relate function class complexity to structure in the function domain. This facilitates risk analysis relative to cluster structure in the input space which is particularly effective in semi-supervised learning. In particular we quantify the complexity of function classes defined over a graph in terms of the graph structure.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:6775
Deposited By:Guy Lever
Deposited On:08 March 2010